Add scrape_samples_scraped to all metric sources (#1081)

* Add scrape_samples_scraped to all metric sources

Signed-off-by: Pete Wall <[email protected]>

* Update examples and tests

Signed-off-by: Pete Wall <[email protected]>

---------

Signed-off-by: Pete Wall <[email protected]>

charts/k8s-monitoring/charts/feature-annotation-autodiscovery/templates/_module.alloy.tpl

@@ -243,7 +243,7 @@ declare "annotation_autodiscovery" {
 {{- if .Values.metricsTuning.includeMetrics }}
     rule {
       source_labels = ["__name__"]
-      regex = "up|{{ join "|" .Values.metricsTuning.includeMetrics }}"
+      regex = "up|scrape_samples_scraped|{{ join "|" .Values.metricsTuning.includeMetrics }}"
       action = "keep"
     }
 {{- end }}

charts/k8s-monitoring/charts/feature-auto-instrumentation/templates/_module.alloy.tpl

@@ -66,7 +66,7 @@ prometheus.relabel "beyla" {
 {{- if $metricAllowList }}
   rule {
     source_labels = ["__name__"]
-    regex = "up|{{ $metricAllowList | join "|" }}"
+    regex = "up|scrape_samples_scraped|{{ $metricAllowList | join "|" }}"
     action = "keep"
   }
 {{- end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_cadvisor.alloy.tpl

@@ -1,10 +1,10 @@
 {{ define "feature.clusterMetrics.cadvisor.allowList" }}
 {{- $allowList := list }}
 {{ if .Values.cadvisor.metricsTuning.useDefaultAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/cadvisor.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/cadvisor.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if .Values.cadvisor.metricsTuning.includeMetrics }}
-{{- $allowList = concat $allowList (list "up") .Values.cadvisor.metricsTuning.includeMetrics -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") .Values.cadvisor.metricsTuning.includeMetrics -}}
 {{ end }}
 {{ $allowList | uniq | toYaml }}
 {{ end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_kepler.alloy.tpl

@@ -1,10 +1,10 @@
 {{ define "feature.clusterMetrics.kepler.allowList" }}
 {{- $allowList := list }}
 {{ if .Values.kepler.metricsTuning.useDefaultAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/kepler.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/kepler.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if .Values.kepler.metricsTuning.includeMetrics }}
-{{- $allowList = concat $allowList (list "up") .Values.kepler.metricsTuning.includeMetrics -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") .Values.kepler.metricsTuning.includeMetrics -}}
 {{ end }}
 {{ $allowList | uniq | toYaml }}
 {{ end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_kube_controller_manager.alloy.tpl

@@ -47,7 +47,7 @@ prometheus.relabel "kube_controller_manager" {
 {{- if $metricAllowList }}
   rule {
     source_labels = ["__name__"]
-    regex = "up|{{ $metricAllowList | join "|" }}"
+    regex = "up|scrape_samples_scraped|{{ $metricAllowList | join "|" }}"
     action = "keep"
   }
 {{- end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_kube_proxy.alloy.tpl

@@ -43,7 +43,7 @@ prometheus.relabel "kube_proxy" {
 {{- if $metricAllowList }}
   rule {
     source_labels = ["__name__"]
-    regex = "up|{{ $metricAllowList | join "|" }}"
+    regex = "up|scrape_samples_scraped|{{ $metricAllowList | join "|" }}"
     action = "keep"
   }
 {{- end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_kube_scheduler.alloy.tpl

@@ -47,7 +47,7 @@ prometheus.relabel "kube_scheduler" {
 {{- if $metricAllowList }}
   rule {
     source_labels = ["__name__"]
-    regex = "up|{{ $metricAllowList | join "|" }}"
+    regex = "up|scrape_samples_scraped|{{ $metricAllowList | join "|" }}"
     action = "keep"
   }
 {{- end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_kube_state_metrics.alloy.tpl

@@ -1,10 +1,10 @@
 {{ define "feature.clusterMetrics.kube_state_metrics.allowList" }}
 {{- $allowList := list }}
 {{ if (index .Values "kube-state-metrics").metricsTuning.useDefaultAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/kube-state-metrics.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/kube-state-metrics.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if (index .Values "kube-state-metrics").metricsTuning.includeMetrics }}
-{{- $allowList = concat $allowList (list "up") (index .Values "kube-state-metrics").metricsTuning.includeMetrics -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (index .Values "kube-state-metrics").metricsTuning.includeMetrics -}}
 {{ end }}
 {{ $allowList | uniq | toYaml }}
 {{ end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_kubelet.alloy.tpl

@@ -1,10 +1,10 @@
 {{ define "feature.clusterMetrics.kubelet.allowList" }}
 {{- $allowList := list }}
 {{ if .Values.kubelet.metricsTuning.useDefaultAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/kubelet.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/kubelet.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if .Values.kubelet.metricsTuning.includeMetrics }}
-{{- $allowList = concat $allowList (list "up") .Values.kubelet.metricsTuning.includeMetrics -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") .Values.kubelet.metricsTuning.includeMetrics -}}
 {{ end }}
 {{ $allowList | uniq | toYaml }}
 {{ end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_kubelet_resource.alloy.tpl

@@ -1,10 +1,10 @@
 {{ define "feature.clusterMetrics.kubeletResource.allowList" }}
 {{- $allowList := list }}
 {{ if .Values.kubeletResource.metricsTuning.useDefaultAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/kubelet_resource.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/kubelet_resource.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if .Values.kubeletResource.metricsTuning.includeMetrics }}
-{{- $allowList = concat $allowList (list "up") .Values.kubeletResource.metricsTuning.includeMetrics -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") .Values.kubeletResource.metricsTuning.includeMetrics -}}
 {{ end }}
 {{ $allowList | uniq | toYaml }}
 {{ end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_node_exporter.alloy.tpl

@@ -1,13 +1,13 @@
 {{- define "feature.clusterMetrics.node_exporter.allowList" }}
 {{- $allowList := list }}
 {{ if (index .Values "node-exporter").metricsTuning.useDefaultAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/node-exporter.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/node-exporter.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if (index .Values "node-exporter").metricsTuning.useIntegrationAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/node-exporter-integration.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/node-exporter-integration.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if (index .Values "node-exporter").metricsTuning.includeMetrics }}
-{{- $allowList = concat $allowList (list "up") (index .Values "node-exporter").metricsTuning.includeMetrics -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (index .Values "node-exporter").metricsTuning.includeMetrics -}}
 {{ end }}
 {{ $allowList | uniq | toYaml }}
 {{- end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_opencost.alloy.tpl

@@ -1,10 +1,10 @@
 {{ define "feature.clusterMetrics.opencost.allowList" }}
 {{- $allowList := list }}
 {{ if .Values.opencost.metricsTuning.useDefaultAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/opencost.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/opencost.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if .Values.opencost.metricsTuning.includeMetrics }}
-{{- $allowList = concat $allowList (list "up") .Values.opencost.metricsTuning.includeMetrics -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") .Values.opencost.metricsTuning.includeMetrics -}}
 {{ end }}
 {{ $allowList | uniq | toYaml }}
 {{ end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/templates/_windows_exporter.alloy.tpl

@@ -1,13 +1,13 @@
 {{- define "feature.clusterMetrics.windows_exporter.allowList" }}
 {{- $allowList := list }}
 {{ if (index .Values "windows-exporter").metricsTuning.useDefaultAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/windows-exporter.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/windows-exporter.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if (index .Values "windows-exporter").metricsTuning.useIntegrationAllowList }}
-{{- $allowList = concat $allowList (list "up") (.Files.Get "default-allow-lists/windows-exporter-integration.yaml" | fromYamlArray) -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (.Files.Get "default-allow-lists/windows-exporter-integration.yaml" | fromYamlArray) -}}
 {{ end }}
 {{ if (index .Values "windows-exporter").metricsTuning.includeMetrics }}
-{{- $allowList = concat $allowList (list "up") (index .Values "windows-exporter").metricsTuning.includeMetrics -}}
+{{- $allowList = concat $allowList (list "up" "scrape_samples_scraped") (index .Values "windows-exporter").metricsTuning.includeMetrics -}}
 {{ end }}
 {{ $allowList | uniq | toYaml }}
 {{- end }}

charts/k8s-monitoring/charts/feature-cluster-metrics/tests/control_plane_test.yaml

@@ -28,7 +28,7 @@ tests:
             
               kubernetes.kubelet "scrape" {
                 clustering = true
-                keep_metrics = "up|go_goroutines|kubelet_certificate_manager_client_expiration_renew_errors|kubelet_certificate_manager_client_ttl_seconds|kubelet_certificate_manager_server_ttl_seconds|kubelet_cgroup_manager_duration_seconds_bucket|kubelet_cgroup_manager_duration_seconds_count|kubelet_node_config_error|kubelet_node_name|kubelet_pleg_relist_duration_seconds_bucket|kubelet_pleg_relist_duration_seconds_count|kubelet_pleg_relist_interval_seconds_bucket|kubelet_pod_start_duration_seconds_bucket|kubelet_pod_start_duration_seconds_count|kubelet_pod_worker_duration_seconds_bucket|kubelet_pod_worker_duration_seconds_count|kubelet_running_container_count|kubelet_running_containers|kubelet_running_pod_count|kubelet_running_pods|kubelet_runtime_operations_errors_total|kubelet_runtime_operations_total|kubelet_server_expiration_renew_errors|kubelet_volume_stats_available_bytes|kubelet_volume_stats_capacity_bytes|kubelet_volume_stats_inodes|kubelet_volume_stats_inodes_free|kubelet_volume_stats_inodes_used|kubelet_volume_stats_used_bytes|kubernetes_build_info|namespace_workload_pod|process_cpu_seconds_total|process_resident_memory_bytes|rest_client_requests_total|storage_operation_duration_seconds_count|storage_operation_errors_total|volume_manager_total_volumes"
+                keep_metrics = "up|scrape_samples_scraped|go_goroutines|kubelet_certificate_manager_client_expiration_renew_errors|kubelet_certificate_manager_client_ttl_seconds|kubelet_certificate_manager_server_ttl_seconds|kubelet_cgroup_manager_duration_seconds_bucket|kubelet_cgroup_manager_duration_seconds_count|kubelet_node_config_error|kubelet_node_name|kubelet_pleg_relist_duration_seconds_bucket|kubelet_pleg_relist_duration_seconds_count|kubelet_pleg_relist_interval_seconds_bucket|kubelet_pod_start_duration_seconds_bucket|kubelet_pod_start_duration_seconds_count|kubelet_pod_worker_duration_seconds_bucket|kubelet_pod_worker_duration_seconds_count|kubelet_running_container_count|kubelet_running_containers|kubelet_running_pod_count|kubelet_running_pods|kubelet_runtime_operations_errors_total|kubelet_runtime_operations_total|kubelet_server_expiration_renew_errors|kubelet_volume_stats_available_bytes|kubelet_volume_stats_capacity_bytes|kubelet_volume_stats_inodes|kubelet_volume_stats_inodes_free|kubelet_volume_stats_inodes_used|kubelet_volume_stats_used_bytes|kubernetes_build_info|namespace_workload_pod|process_cpu_seconds_total|process_resident_memory_bytes|rest_client_requests_total|storage_operation_duration_seconds_count|storage_operation_errors_total|volume_manager_total_volumes"
                 scrape_interval = "60s"
                 max_cache_size = 100000
                 forward_to = argument.metrics_destinations.value
@@ -37,15 +37,15 @@ tests:
               kubernetes.resources "scrape" {
                 clustering = true
                 job_label = "integrations/kubernetes/resources"
-                keep_metrics = "up|node_cpu_usage_seconds_total|node_memory_working_set_bytes"
+                keep_metrics = "up|scrape_samples_scraped|node_cpu_usage_seconds_total|node_memory_working_set_bytes"
                 scrape_interval = "60s"
                 max_cache_size = 100000
                 forward_to = argument.metrics_destinations.value
               }
             
               kubernetes.cadvisor "scrape" {
                 clustering = true
-                keep_metrics = "up|container_cpu_cfs_periods_total|container_cpu_cfs_throttled_periods_total|container_cpu_usage_seconds_total|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_working_set_bytes|container_network_receive_bytes_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total|machine_memory_bytes"
+                keep_metrics = "up|scrape_samples_scraped|container_cpu_cfs_periods_total|container_cpu_cfs_throttled_periods_total|container_cpu_usage_seconds_total|container_fs_reads_bytes_total|container_fs_reads_total|container_fs_writes_bytes_total|container_fs_writes_total|container_memory_cache|container_memory_rss|container_memory_swap|container_memory_working_set_bytes|container_network_receive_bytes_total|container_network_receive_packets_dropped_total|container_network_receive_packets_total|container_network_transmit_bytes_total|container_network_transmit_packets_dropped_total|container_network_transmit_packets_total|machine_memory_bytes"
                 scrape_interval = "60s"
                 max_cache_size = 100000
                 forward_to = [prometheus.relabel.cadvisor.receiver]
@@ -256,7 +256,7 @@ tests:
               kube_state_metrics.scrape "metrics" {
                 targets = kube_state_metrics.kubernetes.targets.output
                 clustering = true
-                keep_metrics = "up|kube_daemonset.*|kube_deployment_metadata_generation|kube_deployment_spec_replicas|kube_deployment_status_condition|kube_deployment_status_observed_generation|kube_deployment_status_replicas_available|kube_deployment_status_replicas_updated|kube_horizontalpodautoscaler_spec_max_replicas|kube_horizontalpodautoscaler_spec_min_replicas|kube_horizontalpodautoscaler_status_current_replicas|kube_horizontalpodautoscaler_status_desired_replicas|kube_job.*|kube_namespace_status_phase|kube_node.*|kube_persistentvolume_status_phase|kube_persistentvolumeclaim_access_mode|kube_persistentvolumeclaim_info|kube_persistentvolumeclaim_labels|kube_persistentvolumeclaim_resource_requests_storage_bytes|kube_persistentvolumeclaim_status_phase|kube_pod_container_info|kube_pod_container_resource_limits|kube_pod_container_resource_requests|kube_pod_container_status_last_terminated_reason|kube_pod_container_status_restarts_total|kube_pod_container_status_waiting_reason|kube_pod_info|kube_pod_owner|kube_pod_spec_volumes_persistentvolumeclaims_info|kube_pod_start_time|kube_pod_status_phase|kube_pod_status_reason|kube_replicaset.*|kube_resourcequota|kube_statefulset.*"
+                keep_metrics = "up|scrape_samples_scraped|kube_daemonset.*|kube_deployment_metadata_generation|kube_deployment_spec_replicas|kube_deployment_status_condition|kube_deployment_status_observed_generation|kube_deployment_status_replicas_available|kube_deployment_status_replicas_updated|kube_horizontalpodautoscaler_spec_max_replicas|kube_horizontalpodautoscaler_spec_min_replicas|kube_horizontalpodautoscaler_status_current_replicas|kube_horizontalpodautoscaler_status_desired_replicas|kube_job.*|kube_namespace_status_phase|kube_node.*|kube_persistentvolume_status_phase|kube_persistentvolumeclaim_access_mode|kube_persistentvolumeclaim_info|kube_persistentvolumeclaim_labels|kube_persistentvolumeclaim_resource_requests_storage_bytes|kube_persistentvolumeclaim_status_phase|kube_pod_container_info|kube_pod_container_resource_limits|kube_pod_container_resource_requests|kube_pod_container_status_last_terminated_reason|kube_pod_container_status_restarts_total|kube_pod_container_status_waiting_reason|kube_pod_info|kube_pod_owner|kube_pod_spec_volumes_persistentvolumeclaims_info|kube_pod_start_time|kube_pod_status_phase|kube_pod_status_reason|kube_replicaset.*|kube_resourcequota|kube_statefulset.*"
                 scrape_interval = "60s"
                 max_cache_size = 100000
                 forward_to = argument.metrics_destinations.value
@@ -289,7 +289,7 @@ tests:
                 targets = discovery.relabel.node_exporter.output
                 job_label = "integrations/node_exporter"
                 clustering = true
-                keep_metrics = "up|node_cpu.*|node_exporter_build_info|node_filesystem.*|node_memory.*|node_network_receive_bytes_total|node_network_receive_drop_total|node_network_transmit_bytes_total|node_network_transmit_drop_total|process_cpu_seconds_total|process_resident_memory_bytes"
+                keep_metrics = "up|scrape_samples_scraped|node_cpu.*|node_exporter_build_info|node_filesystem.*|node_memory.*|node_network_receive_bytes_total|node_network_receive_drop_total|node_network_transmit_bytes_total|node_network_transmit_drop_total|process_cpu_seconds_total|process_resident_memory_bytes"
                 scrape_interval = "60s"
                 max_cache_size = 100000
                 forward_to = argument.metrics_destinations.value
@@ -329,7 +329,7 @@ tests:
                 max_cache_size = 100000
                 rule {
                   source_labels = ["__name__"]
-                  regex = "up|windows_.*|node_cpu_seconds_total|node_filesystem_size_bytes|node_filesystem_avail_bytes|container_cpu_usage_seconds_total"
+                  regex = "up|scrape_samples_scraped|windows_.*|node_cpu_seconds_total|node_filesystem_size_bytes|node_filesystem_avail_bytes|container_cpu_usage_seconds_total"
                   action = "keep"
                 }
                 forward_to = argument.metrics_destinations.value